Subtypes in patients with opioid misuse: A prognostic enrichment strategy using electronic health record data in hospitalized patients.
Adult
Alcoholism
/ diagnosis
Analgesics, Opioid
/ adverse effects
Electronic Health Records
Female
Hospitalization
Humans
Inpatients
Latent Class Analysis
Machine Learning
Male
Middle Aged
Models, Theoretical
Natural Language Processing
Opioid-Related Disorders
/ classification
Patient Discharge
Precision Medicine
Prescription Drug Misuse
/ classification
Prognosis
Tertiary Care Centers
Treatment Outcome
Young Adult
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2019
2019
Historique:
received:
01
05
2019
accepted:
28
06
2019
entrez:
17
7
2019
pubmed:
17
7
2019
medline:
17
3
2020
Statut:
epublish
Résumé
Approaches are needed to better delineate the continuum of opioid misuse that occurs in hospitalized patients. A prognostic enrichment strategy with latent class analysis (LCA) may facilitate treatment strategies in subtypes of opioid misuse. We aim to identify subtypes of patients with opioid misuse and examine the distinctions between the subtypes by examining patient characteristics, topic models from clinical notes, and clinical outcomes. This was an observational study of inpatient hospitalizations at a tertiary care center between 2007 and 2017. Patients with opioid misuse were identified using an operational definition applied to all inpatient encounters. LCA with eight class-defining variables from the electronic health record (EHR) was applied to identify subtypes in the cohort of patients with opioid misuse. Comparisons between subtypes were made using the following approaches: (1) descriptive statistics on patient characteristics and healthcare utilization using EHR data and census-level data; (2) topic models with natural language processing (NLP) from clinical notes; (3) association with hospital outcomes. The analysis cohort was 6,224 (2.7% of all hospitalizations) patient encounters with opioid misuse with a data corpus of 422,147 clinical notes. LCA identified four subtypes with differing patient characteristics, topics from the clinical notes, and hospital outcomes. Class 1 was categorized by high hospital utilization with known opioid-related conditions (36.5%); Class 2 included patients with illicit use, low socioeconomic status, and psychoses (12.8%); Class 3 contained patients with alcohol use disorders with complications (39.2%); and class 4 consisted of those with low hospital utilization and incidental opioid misuse (11.5%). The following hospital outcomes were the highest for each subtype when compared against the other subtypes: readmission for class 1 (13.9% vs. 10.5%, p<0.01); discharge against medical advice for class 2 (12.3% vs. 5.3%, p<0.01); and in-hospital death for classes 3 and 4 (3.2% vs. 1.9%, p<0.01). A 4-class latent model was the most parsimonious model that defined clinically interpretable and relevant subtypes for opioid misuse. Distinct subtypes were delineated after examining multiple domains of EHR data and applying methods in artificial intelligence. The approach with LCA and readily available class-defining substance use variables from the EHR may be applied as a prognostic enrichment strategy for targeted interventions.
Sections du résumé
BACKGROUND
Approaches are needed to better delineate the continuum of opioid misuse that occurs in hospitalized patients. A prognostic enrichment strategy with latent class analysis (LCA) may facilitate treatment strategies in subtypes of opioid misuse. We aim to identify subtypes of patients with opioid misuse and examine the distinctions between the subtypes by examining patient characteristics, topic models from clinical notes, and clinical outcomes.
METHODS
This was an observational study of inpatient hospitalizations at a tertiary care center between 2007 and 2017. Patients with opioid misuse were identified using an operational definition applied to all inpatient encounters. LCA with eight class-defining variables from the electronic health record (EHR) was applied to identify subtypes in the cohort of patients with opioid misuse. Comparisons between subtypes were made using the following approaches: (1) descriptive statistics on patient characteristics and healthcare utilization using EHR data and census-level data; (2) topic models with natural language processing (NLP) from clinical notes; (3) association with hospital outcomes.
FINDINGS
The analysis cohort was 6,224 (2.7% of all hospitalizations) patient encounters with opioid misuse with a data corpus of 422,147 clinical notes. LCA identified four subtypes with differing patient characteristics, topics from the clinical notes, and hospital outcomes. Class 1 was categorized by high hospital utilization with known opioid-related conditions (36.5%); Class 2 included patients with illicit use, low socioeconomic status, and psychoses (12.8%); Class 3 contained patients with alcohol use disorders with complications (39.2%); and class 4 consisted of those with low hospital utilization and incidental opioid misuse (11.5%). The following hospital outcomes were the highest for each subtype when compared against the other subtypes: readmission for class 1 (13.9% vs. 10.5%, p<0.01); discharge against medical advice for class 2 (12.3% vs. 5.3%, p<0.01); and in-hospital death for classes 3 and 4 (3.2% vs. 1.9%, p<0.01).
CONCLUSIONS
A 4-class latent model was the most parsimonious model that defined clinically interpretable and relevant subtypes for opioid misuse. Distinct subtypes were delineated after examining multiple domains of EHR data and applying methods in artificial intelligence. The approach with LCA and readily available class-defining substance use variables from the EHR may be applied as a prognostic enrichment strategy for targeted interventions.
Identifiants
pubmed: 31310611
doi: 10.1371/journal.pone.0219717
pii: PONE-D-19-11087
pmc: PMC6634397
doi:
Substances chimiques
Analgesics, Opioid
0
Types de publication
Journal Article
Observational Study
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0219717Subventions
Organisme : NHLBI NIH HHS
ID : T35 HL120835
Pays : United States
Organisme : NIDA NIH HHS
ID : UG1 DA049467
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR002389
Pays : United States
Organisme : NCATS NIH HHS
ID : U01 TR002398
Pays : United States
Organisme : NIAAA NIH HHS
ID : K23 AA024503
Pays : United States
Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
BMC Public Health. 2011 Aug 10;11:638
pubmed: 21831318
JAMA Psychiatry. 2016 Oct 01;73(10):1064-1071
pubmed: 27626235
J Addict Med. 2019 Jul/Aug;13(4):300-305
pubmed: 30633045
J Am Med Inform Assoc. 2017 May 01;24(3):472-480
pubmed: 27655861
J Stud Alcohol Drugs. 2018 May;79(3):481-489
pubmed: 29885157
Am J Public Health. 2016 Feb;106(2):256-63
pubmed: 26691119
Harm Reduct J. 2017 May 23;14(1):30
pubmed: 28535804
J Addict Med. 2019 Jul/Aug;13(4):306-313
pubmed: 30633044
Health Serv Res. 2009 Apr;44(2 Pt 1):593-605
pubmed: 19040425
Psychol Med. 2019 Jul;49(9):1426-1448
pubmed: 30744717
JAMA. 2016 Apr 19;315(15):1624-45
pubmed: 26977696
BMC Med. 2009 Jun 26;7:31
pubmed: 19558637
Am J Addict. 2005 May-Jun;14(3):256-67
pubmed: 16019976
Drug Alcohol Depend. 2017 Feb 01;171:59-65
pubmed: 28013098
Comput Methods Programs Biomed. 2016 Feb;124:67-75
pubmed: 26614020
Drug Alcohol Depend. 2002 Nov;68 Suppl 1:S57-67
pubmed: 12324175
J Biomed Inform. 2015 Dec;58:28-36
pubmed: 26370451
J Addict Med. 2019 Nov/Dec;13(6):460-463
pubmed: 31689260
J Addict Med. 2018 Nov/Dec;12(6):447-452
pubmed: 29939873
Science. 2016 Nov 4;354(6312):529
pubmed: 27811241
Yearb Med Inform. 2008;:128-44
pubmed: 18660887
Health Serv Res Manag Epidemiol. 2018 Jan 21;5:2333392817747467
pubmed: 29383324
Dev Psychopathol. 1997 Spring;9(2):291-319
pubmed: 9201446
N Engl J Med. 2016 Jan 14;374(2):154-63
pubmed: 26760086
Med Care. 1998 Jul;36(7):1108-13
pubmed: 9674627
Arch Intern Med. 2006 Oct 23;166(19):2087-93
pubmed: 17060538
Am J Epidemiol. 2002 Sep 1;156(5):471-82
pubmed: 12196317
J Biomed Inform. 2018 Oct;86:33-48
pubmed: 30138699
Drug Alcohol Depend. 2007 May;88 Suppl 2:S24-30
pubmed: 17056207
J Am Med Inform Assoc. 2010 Sep-Oct;17(5):507-13
pubmed: 20819853
Addiction. 2016 Nov;111(11):2021-2031
pubmed: 27552496
J Pain. 2010 Dec;11(12):1442-50
pubmed: 20627817
Res Social Adm Pharm. 2017 Nov;13(6):1055-1061
pubmed: 27876595
Pain. 2011 Feb;152(2):397-402
pubmed: 21177035
Psychol Methods. 2012 Dec;17(4):457-477
pubmed: 23025433
Annu Rev Clin Psychol. 2012;8:21-48
pubmed: 22224838
Pain. 2007 Jun;129(3):355-362
pubmed: 17449178
J Pain. 2015 Apr;16(4):380-7
pubmed: 25640294
J Addict Dis. 2015;34(2-3):141-50
pubmed: 26075932
BMC Med Inform Decis Mak. 2015 Apr 17;15:31
pubmed: 25886580
J Subst Abuse Treat. 2018 Feb;85:61-65
pubmed: 28236511
PLoS One. 2017 Jun 8;12(6):e0179054
pubmed: 28594892
Transl Psychiatry. 2016 Oct 18;6(10):e921
pubmed: 27754482
J Am Coll Health. 2017 Apr;65(3):212-216
pubmed: 28059635
J Biomed Inform. 2015 Jun;55:82-93
pubmed: 25841328
Prev Med. 2019 Apr;121:94-98
pubmed: 30763631
JAMA. 2016 Dec 27;316(24):2647-2656
pubmed: 28027367
Ann Transl Med. 2018 Apr;6(7):119
pubmed: 29955579
PLoS One. 2011;6(11):e27244
pubmed: 22087270
J Am Med Inform Assoc. 2016 Sep;23(5):1007-15
pubmed: 26911811